fix: 修复 MLA 多个 bug 并缩小测试模型参数

- MLA kv_b_proj 输出维度和 q_rope 切分偏移修复
- 打通 MLA 配置从 ModelConfig 到 DecoderBlock 的传递路径
- rope_theta 配置不再被忽略，MLA 使用 qk_rope_head_dim
- tie_weight 使用 is True 避免 None 隐式生效
- norm_eps/rope base 类型标注修正
- 测试模型参数缩小 (dim=8, head_dim=4)
- 新增 6 种架构配置 × 2 场景的前向传播测试

astrai/model/components/decoder_block.py

@@ -16,13 +16,13 @@ class DecoderBlock(nn.Module):
         n_heads: int,
         dim_ffn: int,
         n_kv_heads: int,
-        norm_eps: int,
+        norm_eps: float,
         use_qk_norm: bool,
         use_gated_attention: bool,
         layer_id: int,
         attn_type: str = "gqa",
         ffn_type: str = "mlp",
-        **moe_kwargs,
+        **kwargs,
     ):
         super().__init__()
         self.attention = AttnFactory.create(
@@ -34,10 +34,11 @@ class DecoderBlock(nn.Module):
             norm_eps=norm_eps,
             use_gated_attention=use_gated_attention,
             layer_id=layer_id,
+            **kwargs,
         )
         self.input_norm = RMSNorm(dim, norm_eps)
         self.post_attention_norm = RMSNorm(dim, norm_eps)
-        self.mlp = FFNFactory.create(ffn_type, dim, dim_ffn, **moe_kwargs)
+        self.mlp = FFNFactory.create(ffn_type, dim, dim_ffn, **kwargs)
 
     def forward(
         self,